Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    classical conditioning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    domain
    -0.08
     बल
    -0.07
    .Boolean
    -0.07
     Blow
    -0.07
     kang
    -0.06
    より
    -0.06
     Control
    -0.06
    969
    -0.06
    Tester
    -0.06
     CAB
    -0.06
    POSITIVE LOGITS
    .kind
    0.07
    Đ
    0.06
     pinpoint
    0.06
    mot
    0.06
    uido
    0.06
    ують
    0.06
    (prev
    0.06
     intuit
    0.06
     motion
    0.06
    						
↵
    0.06
    Act Density 0.011%

    No Known Activations